FlatMagic: Improving Flat Colorization through AI-driven Design for Digital Comic Professionals
Chuan Yan, John Joon Young Chung, Yoon Kiheon, Yotam I. Gingold, Eytan Adar, Sungsoo Ray Hong
摘要
Creating digital comics involves multiple stages, some creative and some menial. For example, coloring a comic requires a labor-intensive stage known as 'flatting, ' or masking segments of continuous color, as well as creative shading, lighting, and stylization stages. The use of AI can automate the colorization process, but early efforts have revealed limitations-technical and UX-to full automation. Via a formative study of professionals, we identify flatting as a bottleneck and key target of opportunity for human-guided AI-driven automation. Based on this insight, we built FlatMagic, an interactive, AI-driven flat colorization support tool for Photoshop. Our user studies found that using FlatMagic significantly reduced professionals' real and perceived effort versus their current practice. While participants effectively used FlatMagic, we also identified potential constraints in interactions with AI and partially automated workflows. We reflect on implications for comic-focused tools and the benefits and pitfalls of intermediate representations and partial automation in designing human-AI collaboration tools for professionals.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper16
- Understanding Design Collaboration Between Designers and Artificial Intelligence: A Systematic Literature ReviewYang Shi, Tian Gao, Xiaohan Jiao, Nan CaoCSCW 2023 · 被引用 170 次
- PromptCharm: Text-to-Image Generation through Multi-modal Prompting and RefinementZhijie Wang, Yuheng Huang, Da Song, Lei Ma 等CHI 2024 · 被引用 111 次
- PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like InteractionsJohn Joon Young Chung, Eytan AdarUIST 2023 · 被引用 94 次
- "It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language ModelsQian Wan, Siying Hu, Yu Zhang, Piaohong Wang 等CSCW 2024 · 被引用 86 次
- TypeDance: Creating Semantic Typographic Logos from Image through Personalized GenerationShishi Xiao, Liangwei Wang, Xiaojuan Ma, Wei ZengCHI 2024 · 被引用 35 次
它引用的顶会 Paper7
- Towards Vivid and Diverse Image Colorization with Generative Color PriorYanze Wu, Xintao Wang, Yu Li, Honglun Zhang 等ICCV 2021 · 被引用 123 次
- ICONATE: Automatic Compound Icon Generation and IdeationNanxuan Zhao, Nam Wook Kim, Laura Mariah Herman, Hanspeter Pfister 等CHI 2020 · 被引用 49 次
- EmoG: Supporting the Sketching of Emotional Expressions for StoryboardingYang Shi, Nan Cao, Xiaojuan Ma, Siji Chen 等CHI 2020 · 被引用 48 次
- Deep Edge-Aware Interactive Colorization against Color-Bleeding EffectsEungyeup Kim, Sanghyeon Lee, Jeonghoon Park, Somi Choi 等ICCV 2021 · 被引用 34 次
- Instance-Aware Image ColorizationJheng-Wei Su, Hung-Kuo Chu, Jia-Bin HuangCVPR 2020
相关 Paper
- ShadowMagic: Designing Human-AI Collaborative Support for Comic Professionals' ShadowingAmrita Ganguly, Chuan Yan, John Joon Young Chung, Tong Steven Sun 等UIST 2024 · 被引用 8 次
- No Pixel Left Behind: Filling Gaps in Anime ColorizationMasahiro Kono, Akinobu Maejima, Yuki Koyama, Yotam Sechayk 等CHI 2026 · 被引用 1 次
- FlatGAN: A Holistic Approach for Robust Flat-Coloring in High-Definition with Understanding Line DiscontinuityHan Kim, Chunggi Lee, Junsoo Lee, Dohyun Kim 等ACM MM 2023 · 被引用 1 次
- Exploring Interactive Color Palettes for Abstraction-Driven Exploratory Image ColorizationXinyu Shi, Mingyu Liu, Ziqi Zhou, Ali Neshati 等CHI 2024 · 被引用 9 次
- AniDoc: Animation Creation Made EasierYihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang 等CVPR 2025
